Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines

By Jane Elith, J. Leathwick. 2007

346 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/09f987458e8ed02b7ccfb9a18859bd4672d40867

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

In Ecology

In Nature and Landscape Conservation

Citations in the corpus

Machine Learning Methods Without Tears: A Primer for Ecologists (2008, background): “…and evolutionary computation (genetic algorithms and programming); however, we recognize that other statistical approaches, including generalized additive models and multivariate adaptive regression splines, have also illustrated utility in ecology (e.g., Austin 2007; Elith and Leathwick 2007).”
Species Distribution Modeling in the Tropics: Problems, Potentialities, and the Role of Biological Data for Effective Species Conservation (2009, methodology): “Alternative regression-based models including multivariate adaptive regression splines (MARS, Elith and Leathwick 2007; Guisan et al. 2007), BRUTO (Guisan et al. 2007), generalized dissimilarity model of single species (GDMSS, Guisan et al. 2007), conditional fixed effects logistic regression…”
Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation (2008, background): “We investigate the extent to which such data, called targetgroup background (Elith and Leathwick 2007, Phillips et al. unpubl.)”
Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data. (2009, methodology): “MARS uses piecewise linear fits rather than smooth functions and a fitting procedure that makes it much faster to implement than GAM (Friedman 1991, Elith and Leathwick 2007).”
Hierarchical Species Distribution Models (2016, background): “Data sources and collation protocols can vary widely, but common sources include museum specimens and citizen contributed sightings of a species [7, 27, 46].”
Seven Shortfalls that Beset Large-Scale Knowledge of Biodiversity (2015, background): “However, if the representation of the Grinnellian niche provided by occurrence data is biased (Hortal et al. 2008), then SDMs consistently generate unrealistic results (Rocchini et al. 2011), particularly for rare species (Elith & Leathwick 2007).”
Fistularia commersonii in the Mediterranean Sea: invasion history and distribution modeling based on presence-only records (2013, background): “When sightings have such an incidental character, they are known as presence-only records (Elith and Leathwick 2007).”
Global legume diversity assessment: Concepts, key indicators, and strategies (2013, methodology): “Second, several studies (e.g., Elith & Leathwick, 2007; Phillips & al., 2009) have shown that various modeling methods for presence/ absence data can be applied to presence-only data by using presence data of related species as pseudo-absence data.”
Profile or group discriminative techniques? Generating reliable species distribution models using pseudo‐absences and target‐group absences from natural history collections (2010, methodology): “…groups (Phillips et al., 2009), e.g. all vascular plants rather than a single genus, or (2) considering sites that have been visited by any collector and where the target species has not been collected, similar to the ‘inventory pseudo-absence’ of multiresponse methods (Elith & Leathwick, 2007).”
Habitat modelling of tracking data from multiple marine predators identifies important areas in the Southern Indian Ocean (2018, background): “Further effort should also be directed towards exploring alternative approaches for modelling the distribution and overlap of this set of marine top predators, including multivariate models (e.g., Elith & Leathwick, 2007; Warton et al., 2015).”
Correction note: Poisson point process models solve the “pseudo-absence problem” for presence-only data in ecology (2010, methodology): “Theorem 3.3 below links the above results with the case where pseudo-absences are randomly sampled within the region A , which is a more common approach in ecology than sampling on a regular grid [e.g., Elith and Leathwick (2007); Hernandez et al. (2008)].”